BenchLeader

Claude Opus 4.8 vs Grok 4.7

Full profiles: Claude Opus 4.8 (Anthropic) and Grok 4.7 (SpaceXAI): every benchmark, price and rank.

Updated · Data from 15 sources

As of 16 Nov 2026, Claude Opus 4.8 and Grok 4.7 are neck and neck on quality (61.1 vs 57.4 on the BenchLeader Index, inside the ±4.7 margin), and Grok 4.7 is 3.3× cheaper at $3.00 vs $10.00 per 1M tokens blended. Claude Opus 4.8 leads in every category we measure both in.

Key facts (as of 16 Nov 2026)

  • Claude Opus 4.8 scores 61.1 on the BenchLeader Index and Grok 4.7 scores 57.4 (BenchLeader, 16 Nov 2026).
  • Claude Opus 4.8 costs $10.00 per 1M tokens blended (list price, 16 Nov 2026).
  • Grok 4.7 costs $3.00 per 1M tokens blended (list price, 16 Nov 2026).
  • Of the 51 benchmarks both models have, Grok 4.7 leads 28 (BenchLeader, 16 Nov 2026).

Which to pick for…

The pick's numbers come first. Category scores on the BenchLeader scale (50 is the average model, 15 points one standard deviation). High confidence means a lead of half a standard deviation or more; under one point is called either.

Use casePickWhyConfidence
CodingClaude Opus 4.862 vs 61 category score; SciCode 53.5% vs 57.4%Medium
Agents & tool useEither57 vs 57 category score; Terminal-Bench 23.6% vs 38.8%Either
MathsClaude Opus 4.868 vs 56 category score; FrontierMath Tiers 1–3 80.0% vs 53.0%High
ReasoningClaude Opus 4.864 vs 56 category score; ARC-AGI-1 92.5% vs 89.5%High
KnowledgeClaude Opus 4.861 vs 60 category score; SimpleQA Verified 53.0% vs 56.0%Medium
Long documentsEither63 vs 63 category score; AA-LCR v1.1 77.7% vs 76.7%Either
Chat quality (human preference)–Only Grok 4.7 has an Arena rating (63 category score)Not comparable
Lowest costGrok 4.7$3.00 vs $10.00 per 1M blended; agentic coding session $0.144 vs $0.400–
Fastest first answerClaude Opus 4.839.1 s (Claude Opus 4.8 (max)) vs 55.9 s (Grok 4.7 (xhigh)) to the first answer token–
High volume on a budgetNeither flagshipA smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs–

Key differences

  • Claude Opus 4.8 (max) and Grok 4.7 (xhigh) are neck and neck on quality (61.1 vs 57.4, within the ±4.7 margin).
  • Claude Opus 4.8 (max) is stronger in coding, knowledge, long context, maths, reasoning.
  • Grok 4.7 (xhigh) is 3.3× cheaper ($3.00 vs $10.00 per 1M blended).

At a glance

SpecClaude Opus 4.8Grok 4.7
DeveloperAnthropicSpaceXAI
Released28 May 202621 Sep 2026
Context window (tokens)1,000,000500,000
Compared atClaude Opus 4.8 (max)Grok 4.7 (xhigh)
Open weightsNoNo
Price in / out / cached input per 1M$5.00 / $25.00 / $0.500$2.00 / $6.00 / $0.500

Category by category

Category scores on the BenchLeader scale: 50 is the average evaluated model, 15 points is one standard deviation. A gap under one point is called level.

CategoryClaude Opus 4.8 (max)Grok 4.7 (xhigh)Leader
Reasoning64.155.6Claude Opus 4.8
Coding61.960.9Claude Opus 4.8
Agents & tools56.956.9level
Maths67.755.8Claude Opus 4.8
Knowledge61.059.9Claude Opus 4.8
Instruction following62.1–not comparable
Human preference–62.5not comparable
Multimodal–55.5not comparable
Long context63.462.9level
Composite–52.8not comparable

On one chart

Each domain on the index's own scale, where 50 is an average model. Click a domain to see the benchmarks behind it. Pick up to 5 models from the list.

2550 avg75ReasoningCodingAgents & toolsMathsKnowledgeLong contextClaude Opus 4.8, Reasoning: 64.1Claude Opus 4.8, Coding: 61.9Claude Opus 4.8, Agents & tools: 56.9Claude Opus 4.8, Maths: 67.7Claude Opus 4.8, Knowledge: 61.0Claude Opus 4.8, Long context: 63.4Grok 4.7, Reasoning: 55.6Grok 4.7, Coding: 60.9Grok 4.7, Agents & tools: 56.9Grok 4.7, Maths: 55.8Grok 4.7, Knowledge: 59.9Grok 4.7, Long context: 62.9

Not drawn, measured for fewer than two of these models: Instruction following, Multimodal, Human preference.

Model, click to add or removeIndex

Where sources disagree

Across the 51 benchmarks both have, Claude Opus 4.8 leads 23, Grok 4.7 leads 28. Every overall index that rates both puts Claude Opus 4.8 ahead.

Overall indexClaude Opus 4.8 (max)Grok 4.7 (xhigh)Leader
BenchLeader Index61.157.4neck and neck
Arena Text1482†1443Claude Opus 4.8

Each publisher runs its own tasks, harnesses and effort settings, so their overall verdicts can differ; BenchLeader reconciles them on one scale. † measured at another effort setting of the same model (the publisher did not test the one compared here).

Price, speed and latency

List prices blended at three input tokens per output token. Per-task prices use the token counts on the methodology page. Cost, tokens and time per benchmark task are measured: Artificial Analysis’ averages over its whole Intelligence Index run.

MeasureClaude Opus 4.8 (max)Grok 4.7 (xhigh)
Blended price per 1M tokens$10.00$3.00
Input / output per 1M$5.00 / $25.00$2.00 / $6.00
Cached input per 1M$0.500$0.500
Price per task: chat reply$0.0095$0.0026
Price per task: summarize a 30-page report$0.075$0.028
Price per task: code edit$0.068$0.021
Price per task: agentic coding session$0.400$0.144
Price per task: structured extraction$0.015$0.0052
Agentic coding session, input mostly cached$0.198$0.076
Cost per benchmark task (AA Index)–$7.77
Output tokens per task (AA Index)–105k
Of which reasoning–69k
Time per task (AA Index)–26 min
Output speed85 tok/s68 tok/s
Time to first answer39.1 s55.9 s
Time to a complete answer, last measured 13 Nov 202681.0 s145.5 s

Each model is compared at its best-ranked reasoning-effort setting. Claude Opus 4.8 (max) scores 61.1 and takes 39 s to its first answer token; Claude Opus 4.8 (high) scores 60.4 in 1 s, Claude Opus 4.8 scores 58.7 in 1 s. Grok 4.7 (xhigh) scores 57.4 and takes 56 s to its first answer token; Grok 4.7 (high) scores 56.9 in 35 s, Grok 4.7 (low) scores 55.4 in 10 s. Higher effort means more thinking before the answer: better scores, longer waits and more tokens billed. How reasoning effort changes scores and cost.

Every benchmark

197 benchmarks, grouped by category; each name links to the board and its leaders. † measured at another effort setting of the same model, shown for reference and not counted as a win.

MetricPublisherClaude Opus 4.8 (max)Grok 4.7 (xhigh)
BenchLeader IndexBenchLeader61.157.4
Agents & tools scoreBenchLeader56.956.9
Coding scoreBenchLeader61.960.9
Instruction following scoreBenchLeader62.1–
Knowledge scoreBenchLeader61.059.9
Long context scoreBenchLeader63.462.9
Maths scoreBenchLeader67.755.8
Reasoning scoreBenchLeader64.155.6
Composite scoreBenchLeader–52.8
Human preference scoreBenchLeader–62.5
Multimodal scoreBenchLeader–55.5
Blended price $/MBenchLeader$10.00$3.00
Output speedBenchLeader85 tok/s68 tok/s
Time to first answerBenchLeader39.1 s55.9 s
Context windowBenchLeader1,000,000 tokens500,000 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub91.0%92.7%
SimpleBenchSimpleBench64.8%†–
Arena Hard PromptsArena (LMArena)1505†1466
LiveBench 2.0 ReasoningLiveBench–82.7%
LiveBench 1.0 ReasoningLiveBench89.2%82.7%
GPQA Diamond (AA)Artificial Analysis92.0%–
Humanity's Last Exam (AA)Artificial Analysis48.7%43.1%
HLE-Diamond (AA)Artificial Analysis–23.2%
GPQA Diamond (Vals)Vals AI92.4%–
EnigmaEvalScale AI SEAL23.5%†–
Kagi LLM BenchmarkKagi LLM Benchmark88.8%†–
ARC-AGI-1ARC Prize92.5%89.5%
ARC-AGI-2ARC Prize72.1%†61.4%
ARC-AGI-3ARC Prize1.5%†7.0%
CritPtArtificial Analysis20.9%17.7%
CritPt v2 hard subset (AA)Artificial Analysis–33.5%
MysteryMechanismVals AI–25.2%
HLE-Diamond (Scale)Scale AI SEAL–23.4%†
Arena ExpertArena (LMArena)1514†1478
Chess PuzzlesEpoch AI Benchmarking Hub52.0%41.0%
Mystery Game PuzzlesEpoch AI Benchmarking Hub36.0%29.0%
LMCAEpoch AI Benchmarking Hub57.5%49.4%
DTBenchEpoch AI Benchmarking Hub94.9%96.0%
ForecastBenchForecastBench66.1%–
BTF-3Epoch AI Benchmarking Hub14.0%†–
Show all 197 benchmarks
MetricPublisherClaude Opus 4.8 (max)Grok 4.7 (xhigh)
Coding
SciCodeSciCode53.5%57.4%
WeirdMLWeirdML70.5%†–
FrontierCodeCognition46.5%†47.6%†
GSO-BenchGSO-Bench47.1%†–
Arena CodingArena (LMArena)1529†1493
Arena WebDevArena (LMArena)1536†1641
LiveBench 2.0 CodingLiveBench–73.1%
LiveBench 1.0 CodingLiveBench81.8%77.2%
SciCode (AA)Artificial Analysis54.4%57.4%
LiveCodeBenchVals AI87.8%–
IOIVals AI–57.7%
SWE-bench (Vals)Vals AI88.6%–
Code MigrationVals AI47.3%44.8%
Code Migration v1.1Vals AI–53.2%
ProgramBenchVals AI1.0%0.5%
SWE-bench MultimodalVals AI–42.9%
Vibe Code Bench v1.1Vals AI82.7%86.2%
Vibe Code Bench 1-100 v1.1Vals AI–26.4%
SWE Atlas v1.0: Codebase QnAScale AI SEAL57.3%†–
SWE Atlas v1.0: RefactoringScale AI SEAL46.7%†–
SWE Atlas v1.0: Test WritingScale AI SEAL49.6%†–
SWE Atlas v1.1Scale AI SEAL–62.1%†
SWE Atlas v1.1: Codebase QnAScale AI SEAL–73.4%†
SWE Atlas v1.1: Test WritingScale AI SEAL–64.4%†
SWE Atlas v1.1: RefactoringScale AI SEAL–48.6%†
MirrorCodeEpoch AI Benchmarking Hub65.6%54.4%
Surface Evolver BenchEpoch AI Benchmarking Hub87.5%†–
DeepSWE v1.1Epoch AI Benchmarking Hub59.0%–
CursorBenchCursor–46.3%
ALE-BenchEpoch AI Benchmarking Hub1563.8†1545.8
FrontierSWEEpoch AI Benchmarking Hub–29.5%
WeirdML v3WeirdML–8.4%
Terminal-Bench 4.0 (AA)Artificial Analysis21.7%25.8%
Terminal-Bench 2.1 (AA)Artificial Analysis84.6%–
Startrise FrontendStartrise–75.9%†
GameBench 2 OverallDuelLab GameBench 249.4†63.6†
GameBench 2 by reasoning settingDuelLab GameBench 245.1†71.2
Design Arena WebsiteDesign Arena1250†1244†
FrontierCode 1.1 (AA)Artificial Analysis–33.8%
FrontierCode 2.0 (AA)Artificial Analysis–28.7%
Agents & tools
Terminal-BenchTerminal-Bench23.6%38.8%
OSWorld-Verified 2.0OSWorld20.6%–
Remote Labor IndexScale AI / CAIS8.3%†–
APEX-AgentsMercor48.9%54.6%†
Arena AgentArena (LMArena)–2.6
LiveBench Long AgenticLiveBench–45.3%
LiveBench BrowserLiveBench–49.3%
LiveBench Agentic CodingLiveBench50.5%54.0%
Terminal-Bench HardArtificial Analysis58.3%–
τ²-Bench Telecom (AA)Artificial Analysis94.4%–
Terminal-Bench 2.1 (Vals)Vals AI71.9%73.4%
MCP AtlasScale AI SEAL82.2%–
HiL-BenchScale AI SEAL35.3%†–
τ³-bench Bankingτ²-bench39.7%–
GDPval-AA v2.1, normalised scoreArtificial Analysis–60.7%
GDPval-AA v2.1Artificial Analysis14611717
τ³-Banking (AA)Artificial Analysis34.2%–
ITBench SRE (AA)Artificial Analysis–42.1%
Analyst Agent (AA)Artificial Analysis45.0%52.5%
CyberBenchVals AI–69.5%
Finance Agent v2Vals AI53.9%52.3%
Finance Agent v2.1Vals AI–60.6%
Harvey's Legal Agent Benchmark v1.1Vals AI–18.3%
Harvey's Legal Agent Benchmark v1Vals AI9.6%12.5%
Legal Research BenchVals AI43.8%47.1%
Robo-benchVals AI–0.2%
SkillsBenchVals AI59.2%–
SREBenchVals AI–3.8%
Tax Agent BenchVals AI30.0%35.8%
Terminal-Bench 2.0 (Vals)Vals AI70.0%–
Terminal-Bench 4.0 (Vals)Vals AI23.2%28.8%
Terminal-Bench ScienceVals AI4.3%10.0%
Time Horizon Index: KSPVals AI11.8%–
Arena SearchArena (LMArena)1194†–
Arena Agent Task CompletionArena (LMArena)–5.1
DeepResearch BenchDeepResearch Bench50.2%†–
PostTrainBenchEpoch AI Benchmarking Hub31.0%–
GBAEvalEpoch AI Benchmarking Hub70.9%†–
Vending-Bench 2Andon Labs2992.310536.8†
AutomationBenchArtificial Analysis45.6%65.6%
GDP.pdf (AA)Artificial Analysis22.8%20.0%
Harvey LAB-AA v1.1Harvey–9.4%
EnterpriseOps-GymArtificial Analysis44.0%–
AA-Briefcase v1.1Artificial Analysis13201636
GDPxGDPx by SemiAnalysis–3.9%
Design Arena AgenticDesign Arena1226†1277†
Terminal-Bench-Science 0.1 (AA)Artificial Analysis–11.4%
CWE-Bench (AA)Artificial Analysis–68.3%
DeepSec-Bench (AA)Artificial Analysis–26.9%
CyberGym end-to-end (AA)Artificial Analysis–74.0%
MKA (AA)Artificial Analysis–40.1%
FACTS SearchGoogle–85.6%†
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub80.0%53.0%
FrontierMath Tier 4Epoch AI Benchmarking Hub56.1%17.1%
OTIS Mock AIMEEpoch AI Benchmarking Hub98.3%98.1%
ProofBenchVals AI69.0%26.0%†
LiveBench MathematicsLiveBench94.3%95.7%
AIME 2026MathArena100.0%–
HMMT February 2026MathArena95.5%–
MathArena ApexMathArena81.3%–
Arena MathsArena (LMArena)1476†1447
FrontierMath ErdősEpoch AI Benchmarking Hub–0.0%
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub53.0%56.0%
LiveBench 2.0 Data AnalysisLiveBench–76.9%
LiveBench ResearchLiveBench–89.5%
LiveBench 1.0 Data AnalysisLiveBench66.0%76.9%
AA-Omniscience v1.1Artificial Analysis–31.2
MMLU-ProVals AI89.6%–
LegalBenchVals AI83.6%84.4%
CorpFinVals AI66.7%–
TaxEvalVals AI75.6%–
PRBench LegalScale AI SEAL–47.6%
BioMysteryBenchVals AI–69.3%
Excel Modeling BenchmarkVals AI69.4%67.0%
Excel Modeling Benchmark v1.1Vals AI–71.5%
MedCodeVals AI53.2%49.5%
MedScribeVals AI85.8%89.4%
Public Benefits Bench v1.1Vals AI68.1%65.6%
Access to Justice BenchmarkVals AI–73.7%
Financial Coaching BenchVals AI–74.1%
Immigration BenchVals AI–68.0%
DrugDiscoveryBenchScale AI SEAL46.8%–
EBR-benchEpoch AI Benchmarking Hub28.6%–
GDP.pdfEpoch AI Benchmarking Hub24.0%22.8%
AA-Omniscience v1.1: accuracyArtificial Analysis–42.7%
AA-Omniscience v1.1: non-hallucinationArtificial Analysis–80.0%
HealthBench Professional (AA)OpenAI–55.8%
FACTS ParametricGoogle–54.3%†
Instruction following
LiveBench LanguageLiveBench79.7%80.1%
LiveBench Instruction FollowingLiveBench72.0%75.3%
IFBenchArtificial Analysis62.2%–
Arena Instruction FollowingArena (LMArena)1479†1435
Human preference
Arena TextArena (LMArena)1474†1443
EQ-Bench 4EQ-Bench1268†–
EQ-Bench Creative Writing v3EQ-Bench1840†2012†
Arena Creative WritingArena (LMArena)1464†1421
Arena Multi-turnArena (LMArena)1493†1435
Arena Longer QueriesArena (LMArena)1499†1454
Multimodal
Arena VisionArena (LMArena)1289†1230
LiveBench DesignLiveBench–75.0%
MMMU-ProArtificial Analysis–78.2%†
MMMU-Pro (Vals)Vals AI86.6%–
MortgageTaxVals AI69.9%–
SAGEVals AI–88.7%
Humanity's Sixth SenseScale AI SEAL23.5%–
GeoBenchGeoBench81.0%†61.0%†
Blueprint-Bench 2Epoch AI Benchmarking Hub14.5%†32.5%†
Furniture AssemblyEpoch AI Benchmarking Hub42.5%20.8%
VIALS-AAHandshake AI–37.9%
Code2Video-AAArtificial Analysis–1127
AA-3DArtificial Analysis–992
FACTS MultimodalGoogle–40.9%†
Long context
AA-LCR v1.1Artificial Analysis77.7%76.7%
Arena DocumentArena (LMArena)1476†–
MLCRArtificial Analysis19.4%20.0%
FACTS GroundingGoogle–68.6%†
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub159.9†156.2†
LiveBench 2.0LiveBench–67.9%
LiveBench 1.0LiveBench76.2%77.4%
AA Intelligence Index v5.0.1Artificial Analysis–35.5
AA Intelligence Index v4.3.2Artificial Analysis41.846.5
AA Progress Index v1Artificial Analysis318.4322.7
Vals IndexVals AI–58.6
Vals Finance IndexVals AI–58.8%
Vals RSI IndexVals AI24.0%20.2%
Vals Science IndexVals AI–34.8%
Vals Multimodal IndexVals AI70.9%–
Vals Router IndexVals AI–58.6%†
Vals Legal IndexVals AI–72.7%
AA Cyber IndexArtificial Analysis–56.4
Safety & honesty
FORTRESSScale AI SEAL18.2%–
DistressBenchScale AI SEAL71.4%†52.4%†

Data as of 2026-11-16. Best configuration of each model; every score links to its source on the model pages.

DuelLab GameBench 2, release gb2-20261111-7b598bb13de4 (https://benchmarks.duellab.org/releases/gb2-20261111-7b598bb13de4/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.

What changed

  • Claude Opus 4.8 (max): BenchLeader Index 60.3 → 61.1.
  • Grok 4.7 (xhigh): BenchLeader Index 58.0 → 57.4.
  • Claude Opus 4.8 (max): 27 new results (LiveCodeBench, MMLU-Pro, LegalBench…).
  • Grok 4.7 (xhigh): 8 new results (LiveBench 2.0, LiveBench Long Agentic, LiveBench 2.0 Reasoning…).
  • Claude Opus 4.8 (max): 1 new result (GDPval-AA v2.1).
  • Claude Opus 4.8 (max): 1 score revision.
  • Claude Opus 4.8 (max): 1 new result (MirrorCode).
  • Grok 4.7 (xhigh): 1 new result (MirrorCode).
  • Grok 4.7 (xhigh): 1 new result (ALE-Bench).
  • Grok 4.7 (xhigh): 2 score revisions.

Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs

Claude Opus 4.8 vs Grok 4.7: questions

Is Claude Opus 4.8 better than Grok 4.7?
Claude Opus 4.8 (max) and Grok 4.7 (xhigh) are neck and neck on quality (61.1 vs 57.4, within the ±4.7 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 16 Nov 2026, so check the category scores for your use.
Claude Opus 4.8 vs Grok 4.7: which is cheaper, and will that change?
Grok 4.7 is cheaper today: $3.00 against $10.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is Claude Opus 4.8 or Grok 4.7 better for coding?
Claude Opus 4.8 scores higher in coding (62 vs 61 on the category index, where 50 is average). On SciCode, the top shared coding benchmark, it is 53.5% for Claude Opus 4.8 against 57.4% for Grok 4.7.
Which is faster, Claude Opus 4.8 or Grok 4.7?
Claude Opus 4.8 streams faster (85 vs 68 output tokens per second, Artificial Analysis 7-day median).
Is Claude Opus 4.8 or Grok 4.7 better for agents and tool use?
They are level in agentic tasks (57 vs 57 on the category index). On Terminal-Bench, the top shared agents & tools benchmark, it is 23.6% for Claude Opus 4.8 against 38.8% for Grok 4.7.
More questions (4)
Which is better for long documents?
They are level on long-context benchmarks (63 vs 63). Claude Opus 4.8 accepts more context: 1,000,000 against 500,000 tokens for Grok 4.7.
Which has lower latency?
Claude Opus 4.8 answers first: 39.1 s against 55.9 s to the first answer token, as Artificial Analysis measures it. Reasoning effort drives most of this: a higher setting thinks longer before it answers.
Do independent benchmarks agree on Claude Opus 4.8 vs Grok 4.7?
Across the 51 benchmarks both have, Claude Opus 4.8 leads 23, Grok 4.7 leads 28. Every overall index that rates both puts Claude Opus 4.8 ahead.
When was Grok 4.7 released?
Grok 4.7 was released on 21 Sep 2026.